AI
WISE-ATTA: When to Ask for Labels in Budgeted Active Test-Time Adaptation
Publication: Hugging Face Daily Papers
Author: Not available in collected metadata
Source published: 28/09/2026, 20:00:00 UTC
Briefing created: 30/09/2026, 11:01:27 UTC
Based on a feed excerpt; full article content has not been acquired. Source evidence retrieved 30/09/2026, 10:18:24 UTC.
Briefings
WISE-ATTA introduces budgeted Active Test-Time Adaptation where labels are available for only a fraction of test batches, shifting the challenge from batch-level selection to temporal supervision allocation. The method uses lightweight online signals to prioritize useful periods and a drift-based criterion to select samples with ongoing adaptation dynamics, achieving competitive performance on synthetic and natural distribution shifts while requiring substantially fewer labels than prior methods.
Key points
- WISE-ATTA allocates supervision over the test stream based on lightweight signals computed online, prioritizing periods where supervision is likely to be most useful.
- The method employs a drift-based sample selection criterion that targets samples exhibiting ongoing, unconverged adaptation dynamics, enabling effective updates from a single labeled example.
Context and limitations
Evaluation is limited to synthetic corruptions (ImageNet-C) and natural distribution shifts (ImageNet-R/K/A) across settings; code availability is restricted to GitHub without public access details.
Generated by Bittrees-hosted qwen35-2b sha256:aaf42c8b7c3c on 30/09/2026, 11:01:27 UTC. Based on publisher-provided feed evidence; may not cover the full original article. Check the source for details.
View archived briefing on IPFS
bafybeihtcrbrui4y4okff52mdvpoffthahzf4h3gdx7etwihpub4f5ig5a